基于句法信息的书读前后非分句语言片段识别  

Automatic Identification of Non-clause Fragments between Punctuation Based on Syntactic Knowledge

作　　者：李琼[1] 李志[1] 

机构地区：[1]华中师范大学国际文化交流学院,湖北武汉430079

出　　处：《重庆邮电大学学报（社会科学版）》2010年第2期63-66,90,共5页Journal of Chongqing University of Posts and Telecommunications(Social Science Edition)

基　　金：华中师范大学"丹桂计划"基金资助项目

摘　　要：基于句法信息的书读前后非分句语言识别和标注是现代汉语复句语料库建设工作的一部分。首先对文章的题目进行了阐释,接着论述了句法知识在中文信息处理中的作用,然后基于有关的句法信息制定了五条可程序化后供计算机执行的规则,最后给出了实验结果及分析。Automatic identification and labeling of non-clause phrase between punctuation based on syntactic knowledge is part of the construction of Modern Chinese Corpus. First this paper explains the subject, and then it discusses the role the syntactic knowledge plays in CIP and supplies five rules based on syntactic knowledge with the computer to execute after programming. Finally, the paper does an experiment with the given rules and makes a conclusion.

关 键 词：书读前后语言片段 非分句 句法 形式标记 规则 

分 类 号：H08[语言文字—语言学]